megapot
On-chain USDC lottery on Base with daily drawings. Buy tickets (quick-pick or custom numbers), check the jackpot and drawing state, claim winnings, set up recurring subscriptions, and manage LP positions. Trigger on "megapot", "lottery ticket", "jackpot", "quick pick", or "did I win".
71
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Medium
Suggest reviewing before use
W009: Direct money access capability detected (payment gateways, crypto, banking).
What this means
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Why it was flagged
The skill explicitly enables and instructs on-chain financial operations: it lists contract and USDC addresses and ABIs, maps user intents to specific purchase/subscribe/deposit/withdraw/claim tasks, requires the Bankr skill "for wallet operations (signing, submitting transactions on Base)", instructs using Bankr's wallet tools to execute transactions and ERC-20 approve calls, and mandates parameters for purchase transactions. These are specific crypto transaction capabilities (sending transactions, approving spenders, buying tickets, depositing/withdrawing LP, claiming payouts) — not generic browser or HTTP tooling — so this grants direct financial execution authority.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Runtime workflow ingests user-influenced free text into the decision tree to route tasks, and the subsequent “claim winnings” flow fetches from `https://api.megapot.io/v1/wallets/{userWallet}/wins?...` where `{userWallet}` is derived from the user-provided context, so the model can process outsider-authored text (the user request) without first selecting a specific trusted item.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
I flagged the llms.megapot.io endpoints (e.g. https://llms.megapot.io/ and its /tasks/... and /abi/... paths) because SKILL.md explicitly tells the agent to fetch task pages and ABIs from those URLs at task time, meaning remotely-hosted content will be fetched at runtime and directly controls the agent's instructions/recipes.
- Repository
- BankrBot/skills
- Path
megapot/SKILL.md
- Commit
48bc585
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.